The GeForce GTX 1060 Founders Edition & ASUS Strix GTX 1060 Review
by Ryan Smith on August 5, 2016 2:00 PM ESTCompute
Shifting gears, let’s take a look at compute performance on GTX 1060.
As we already had the chance to categorize the Pascal architecture’s compute performance in our GTX 1080 review, there shouldn’t be any surprises here. But it will be interesting to see whether the GTX 1060’s higher ratio of memory bandwidth per FLOP materially impacts overall compute performance.
Starting us off for our look at compute is LuxMark3.1, the latest version of the official benchmark of LuxRender. LuxRender’s GPU-accelerated rendering mode is an OpenCL based ray tracer that forms a part of the larger LuxRender suite. Ray tracing has become a stronghold for GPUs in recent years as ray tracing maps well to GPU pipelines, allowing artists to render scenes much more quickly than with CPUs alone.
While GTX 1060 could hang with GTX 980 in gaming benchmarks, we don’t start off the same way with compute benchmarks, with the last-generation flagship holding about 17% ahead. Unfortunately for NVIDIA, this is about where GTX 1060 needed to be to best RX 480; instead it ends up trailing the AMD competition. Otherwise the performance gain versus the GTX 960 stands at 65%.
For our second set of compute benchmarks we have CompuBench 1.5, the successor to CLBenchmark. CompuBench offers a wide array of different practical compute workloads, and we’ve decided to focus on face detection, optical flow modeling, and particle simulations.
Like with GTX 1080, relative performance is all over the place. GTX 1060 wins with face detection, loses at optical flow, and wins again at particle simulation. Even the gains versus GTX 960 are a bit more uneven, though at the end of the day GTX 1060 ends up being significantly faster than its predecessor with all 3 sub-benchmarks.
Moving on, our 3rd compute benchmark is the next generation release of FAHBench, the official Folding @ Home benchmark. Folding @ Home is the popular Stanford-backed research and distributed computing initiative that has work distributed to millions of volunteer computers over the internet, each of which is responsible for a tiny slice of a protein folding simulation. FAHBench can test both single precision and double precision floating point performance, with single precision being the most useful metric for most consumer cards due to their low double precision performance. Each precision has two modes, explicit and implicit, the difference being whether water atoms are included in the simulation, which adds quite a bit of work and overhead. This is another OpenCL test, utilizing the OpenCL path for FAHCore 21.
Finally, in Folding@Home, we see the usual split between single precision and double precision performance. GTX 1060 is solidly in the lead when using FP32, but NVIDIA’s poor FP64 rate means that if double precision is needed, RX 480 will pull ahead.
Facebook
Twitter
RSS
189 Comments
View All Comments
Mikuni - Saturday, August 6, 2016 - link
Avidemux works pretty well.onemoar@gmail.com - Saturday, August 6, 2016 - link
here is my luxmark scoreoverclocked EVGA GTX 1060SC
http://www.luxmark.info/node/2919
Mustalainen - Saturday, August 6, 2016 - link
I think i have commented once or twice on any article here but just had to do it again. The people in the comment section are just out right arrogant. You expect the reviewer to provide the detailed reviews on the same day a product is released? Can you guys cut the guys at Anandtech some slack? I bet they do their best in order to provide us with these reviews (which by the way are free). If you are not happy with the quality of the article, go somewhere else (but i bet you always come back here just because these guys do a great job). So what if the review is lagging with a month or two, if you are such an enthusiast go and buy the card/device yourself.fanofanand - Saturday, August 6, 2016 - link
They would receive their samples weeks ahead of time. How do you think so many day 1 reviews get posted?Sushisamurai - Saturday, August 6, 2016 - link
there is some truth to @fanofanand, but that's assuming anandtech also gets their review samples ahead of time as well - which you really can't prove. Those assumptions can be toxic.Mustalainen - Sunday, August 7, 2016 - link
So assuming this is not the authors full time job they should try to rush the review for the release date? And as stated in the other comment, you can only assume they get review samples ahead of time? There are so many day 1 reviews from other sources because when they have receive the review sample the review is about reading the technical details on the box (and test 5-10 different games and report the fps if its a gpu). Do you want Anandtech to become such an site?yannigr2 - Saturday, August 6, 2016 - link
This review makes GTX 1060 look much better than RX 480, compared to other reviews. Just an observation.MarkieGcolor - Saturday, August 6, 2016 - link
Agreed. AMD really needs to release their high end. I wonder if they are in cahoots with Nvidia. Why wouldn't they release a card that can beat titan x when they totally could? With this new process both companies are holding backsilverblue - Sunday, August 7, 2016 - link
Vega isn't ready yet, that's why they've not done it.Jman13 - Tuesday, August 9, 2016 - link
That's because they ignored a lot of things where the 480 is better: such as DX12 on RotTR, where the 480 pulls essentially even with the 1060. The games list also ignores Doom, which is a HUGE win for the 480, and is included in most other review sites games suites. I understand the difficulty in altering and adding games to the suite, but I do think the discussion could have focused on the fact that there is a split between these two cards depending on which APIs are used. The 1060 is clearly the better card in DX 11 games. The 480 has generally performed very well in DX 12 games, being even in some and notably better in others. The only Vulkan game, Doom, shows a HUGE lead for the RX 480, but who knows how representative that is at this point.Long term, the 480 will probably be the faster card for newer games that use DX12, while the 1060 will be faster for most current and older games, as well as several newer games for the next year.